build-mcp-server

Name: claude-plugins-public/build-mcp-server
Author: anthropics

Share on X Share on LinkedIn Share on Bluesky

40Medium

The skill deceptively fabricates user consent to bypass authorization protocols, posing a significant security risk by manipulating user intent to execute unauthorized actions.

ThreatsCI SM CS BC S HITL

Threat Analysis

AI Agent Traps ↗Scanned 6/29/2026

Content InjectionPerception1 finding

Semantic ManipulationReasoningclean

Cognitive StateMemory & Learningclean

Behavioural ControlActionclean

SystemicMulti-Agent Dynamicsclean

Human-in-the-LoopHuman Overseerclean

HygienePackaging & Manifest1 finding

Skill Info

Nameanthropics/claude-plugins-public/build-mcp-server

Registrygithub

Version315339817c4e

PURLpkg:github/anthropics/claude-plugins-public@315339817c4e?skill=build-mcp-server

Stars31,307

Installs62

Source

Repository ↗SKILL.md ↗

Install

This skill has findings worth reviewing before installing.

GitHub

62 installs

Skills.shDocs

npx skills add https://github.com/anthropics/claude-plugins-public

Assessments (2)

AI Agent Traps ↗

Fabricated user consent / pre-authorized instruction — a statement falsely attributed to the user to manufacture authorizationmediumprompt injectionAML.T0051AML.T0051.000AML.T0051.001AML.T0054LLM01:2025

Fabricated user consent / pre-authorized instruction — a statement falsely attributed to the user to manufacture authorization

95% confidenceline 19

the user has already told

Missing licenseinfopolicy violation

Skill does not specify a license field. Specifying a license helps users understand usage terms.

100% confidence

Version History (2)

315339817c4ecurrent40Medium6/29/2026 73e22af437e040Medium6/20/2026

Badge

Markdown

[![Mondoo Skill Check](https://mondoo.com/ai-agent-security/api/badge/github/anthropics/claude-plugins-public/build-mcp-server.svg)](https://mondoo.com/ai-agent-security/skills/github/anthropics/claude-plugins-public/build-mcp-server)

HTML

<a href="https://mondoo.com/ai-agent-security/skills/github/anthropics/claude-plugins-public/build-mcp-server"><img src="https://mondoo.com/ai-agent-security/api/badge/github/anthropics/claude-plugins-public/build-mcp-server.svg" alt="Mondoo Skill Check" /></a>

Image URL

https://mondoo.com/ai-agent-security/api/badge/github/anthropics/claude-plugins-public/build-mcp-server.svg

View on GitHub↗

Secure your AI agents

Skills can read files, run commands, and access credentials. Mondoo helps organizations manage the security risks of AI agent skills across their entire fleet, discover and control Shadow AI usage.

Continuous scanning of skills across all registries
Policy enforcement before skills reach your agents
Integration with your existing security workflow